Kang X, Xu Y, Wu X, Liang Y, Wang C, Guo J et al.. Proteomic fingerprints for potential application to early diagnosis of severe acute respiratory syndrome. Clin Chem 51: 56-64

Academy of Military Medical Sciences, T’ien-ching-shih, Tianjin Shi, China
Clinical Chemistry (Impact Factor: 7.91). 01/2005; 51(1):56-64. DOI: 10.1373/clinchem.2004.032458
Source: PubMed


Definitive early-stage diagnosis of severe acute respiratory syndrome (SARS) is important despite the number of laboratory tests that have been developed to complement clinical features and epidemiologic data in case definition. Pathologic changes in response to viral infection might be reflected in proteomic patterns in sera of SARS patients.
We developed a mass spectrometric decision tree classification algorithm using surface-enhanced laser desorption/ionization time-of-flight mass spectrometry. Serum samples were grouped into acute SARS (n = 74; <7 days after onset of fever) and non-SARS [n = 1067; fever and influenza A (n = 203), pneumonia (n = 176); lung cancer (n = 29); and healthy controls (n = 659)] cohorts. Diluted samples were applied to WCX-2 ProteinChip arrays (Ciphergen), and the bound proteins were assessed on a ProteinChip Reader (Model PBS II). Bioinformatic calculations were performed with Biomarker Wizard software 3.1.1 (Ciphergen).
The discriminatory classifier with a panel of four biomarkers determined in the training set could precisely detect 36 of 37 (sensitivity, 97.3%) acute SARS and 987 of 993 (specificity, 99.4%) non-SARS samples. More importantly, this classifier accurately distinguished acute SARS from fever and influenza with 100% specificity (187 of 187).
This method is suitable for preliminary assessment of SARS and could potentially serve as a useful tool for early diagnosis.

Download full-text


Available from: Youchun Wang, Sep 08, 2014
  • Source
    • "Proteomic analysis provides a unique tool for the identification of diagnostic biomarkers, evaluation of disease progression and development of drugs [41]. SELDI-TOF-MS has been used to resolve proteins in biological specimens through binding to biochemically distinct ProteinChips [34], [42], and has many other advantages compared with traditional approaches: 1) it is much faster to perform; 2) it has high-throughput capability; 3) it requires only small amount of protein sample; 4) it has relatively high sensitivity to detect proteins at picomole to attamole range; 5) it can effectively resolve low mass proteins (2–20 KDa) and 6) it is directly applicable for development of clinical assays [26]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Neural tube defects (NTDs) are common birth defects, whose specific biomarkers are needed. The purpose of this pilot study is to determine whether protein profiling in NTD-mothers differ from normal controls using SELDI-TOF-MS. ProteinChip Biomarker System was used to evaluate 82 maternal serum samples, 78 urine samples and 76 amniotic fluid samples. The validity of classification tree was then challenged with a blind test set including another 20 NTD-mothers and 18 controls in serum samples, and another 19 NTD-mothers and 17 controls in urine samples, and another 20 NTD-mothers and 17 controls in amniotic fluid samples. Eight proteins detected in serum samples were up-regulated and four proteins were down-regulated in the NTD group. Four proteins detected in urine samples were up-regulated and one protein was down-regulated in the NTD group. Six proteins detected in amniotic fluid samples were up-regulated and one protein was down-regulated in the NTD group. The classification tree for serum samples separated NTDs from healthy individuals, achieving a sensitivity of 91% and a specificity of 97% in the training set, and achieving a sensitivity of 90% and a specificity of 97% and a positive predictive value of 95% in the test set. The classification tree for urine samples separated NTDs from controls, achieving a sensitivity of 95% and a specificity of 94% in the training set, and achieving a sensitivity of 89% and a specificity of 82% and a positive predictive value of 85% in the test set. The classification tree for amniotic fluid samples separated NTDs from controls, achieving a sensitivity of 93% and a specificity of 89% in the training set, and achieving a sensitivity of 90% and a specificity of 88% and a positive predictive value of 90% in the test set. These suggest that SELDI-TOF-MS is an additional method for NTDs pregnancies detection.
    PLoS ONE 07/2014; 9(7):e103276. DOI:10.1371/journal.pone.0103276 · 3.23 Impact Factor
  • Source
    • "There are many variants of decision trees; in the simplest form, 'yes'/'no' paths are followed throughout the classification process; in others, probability distributions over the classes are used in order to estimate the conditional probability that an item reaching a leaf belongs to the class if defines [39]. In biology, it has been used in Parkinson's disease management [40], disease severity profiling [41,42], toxicity analysis [43], large-scale proteomic studies [44,45], microarray data classification [46] and phylogenetic analysis, among other applications. Depending on the number of factors that will be considered to classify the samples, decision trees may be made by hand or constructed automatically using a learning or an optimization algorithm [38,47]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: All polypeptide backbones have the potential to form amyloid fibrils, which are associated with a number of degenerative disorders. However, the likelihood that amyloidosis would actually occur under physiological conditions depends largely on the amino acid composition of a protein. We explore using a naive Bayesian classifier and a weighted decision tree for predicting the amyloidogenicity of immunoglobulin sequences. The average accuracy based on leave-one-out (LOO) cross validation of a Bayesian classifier generated from 143 amyloidogenic sequences is 60.84%. This is consistent with the average accuracy of 61.15% for a holdout test set comprised of 103 AM and 28 non-amyloidogenic sequences. The LOO cross validation accuracy increases to 81.08% when the training set is augmented by the holdout test set. In comparison, the average classification accuracy for the holdout test set obtained using a decision tree is 78.64%. Non-amyloidogenic sequences are predicted with average LOO cross validation accuracies between 74.05% and 77.24% using the Bayesian classifier, depending on the training set size. The accuracy for the holdout test set was 89%. For the decision tree, the non-amyloidogenic prediction accuracy is 75.00%. This exploratory study indicates that both classification methods may be promising in providing straightforward predictions on the amyloidogenicity of a sequence. Nevertheless, the number of available sequences that satisfy the premises of this study are limited, and are consequently smaller than the ideal training set size. Increasing the size of the training set clearly increases the accuracy, and the expansion of the training set to include not only more derivatives, but more alignments, would make the method more sound. The accuracy of the classifiers may also be improved when additional factors, such as structural and physico-chemical data, are considered. The development of this type of classifier has significant applications in evaluating engineered antibodies, and may be adapted for evaluating engineered proteins in general.
    BMC Bioinformatics 02/2010; 11(1):79. DOI:10.1186/1471-2105-11-79 · 2.58 Impact Factor
  • Source
    • "A new method for diagnosing the early stage of PBC is still an unmet need in clinical practice. Proteomics has been shown to be a promising method for the early detection of cancer, neuropathic disease, infectious disease, and rheumatic diseases (Shiwa et al., 2003; Dotzlaw et al., 2004; De Seny et al., 2005; Kang et al., 2005; Agranoff et al., 2006). In this study, we use proteomic approaches to identify relevant biomarkers that could replace invasive and nonspecific tests for the early diagnosis of PBC. "
    [Show abstract] [Hide abstract]
    ABSTRACT: (PBC) is not a rare disease worldwide. Most patients are diagnosed at the advanced stage, primarily because there are not yet any valid biomarkers available for early diagnosis. Useful biomarkers are absolutely necessary for early detection of PBC. Fortunately, the use of MALDI-TOF-MS and pattern recognition software has been successful in finding specific markers for the early detection of the disease. To screen for potential protein biomarkers in the serum for diagnosing PBC, MALDI-TOF-MS combined with magnetic beads and pattern recognition software was used to investigate 119 serum samples from 44 patients with PBC, 32 controls with other hepatic disease, and 43 healthy controls. A total of 69 discriminant m/z peaks were identified as being associated with PBC. Of them, the m/z peaks at 3445, 4260, 8133, and 16,290 were used to construct a model for the diagnosis of PBC. This diagnostic model can distinguish PBC from non-PBC controls with a sensitivity of 93.3% and a specificity of 95.1%. In our blind test, it demonstrated good sensitivity and specificity: 92.9% and 82.4%, respectively. These results indicate that useful serum biomarkers for PBC can be discovered by MALDI-TOF-MS combined with the use of magnetic beads and pattern recognition software. The pattern of multiple markers provides a powerful and reliable diagnostic method for PBC with high sensitivity and specificity.
    The Anatomical Record Advances in Integrative Anatomy and Evolutionary Biology 03/2009; 292(3):455-60. DOI:10.1002/ar.20870 · 1.54 Impact Factor
Show more